检索结果-内蒙古大学图书馆

Joint 13th International Conference on soft Computing and Intelligent systems and 25th International symposium on Advanced Intelligent systems, sCIs and IsIs 2024

作者： Miyakawa, Hiroki Endo, Yasunori Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master's Program in Risk and Resilience Engineering University of Tsukuba Ibaraki Tsukuba Japan Institute of Systems and Information Engineering University of Tsukuba Ibaraki Tsukuba Japan

ISBN: (纸本)9798350373332

Clustering is a typical unsupervised learning method for classifying unsupervised data. One of the clustering meth-ods, even-sized clustering based on optimization (ECBO), is a clustering algorithm that imposes a constraint to equalize the size of each cluster. ECBO has been suggested to be effective in delivery and other problems. However, it is limited to Euclidean space. On the other hand, spectral clustering with a wide range of applicability for partitioning graph data has been proposed. In this paper, we propose even-sized spectral clustering, which imposes a size-equal constraint on spectral clustering, and show that it is an extension of the graph partitioning problem. We also verify the validity of the results through numerical examples. © 2024 IEEE.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

On a New Rough Clustering Based on Optimization 13

On a New Rough Clustering Based on Optimization

引用

Joint 13th International Conference on soft Computing and Intelligent systems and 25th International symposium on Advanced Intelligent systems, sCIs and IsIs 2024

作者： Furuta, sakuya Endo, Yasunori Master's Program in Risk and Resilience Engineering Degree Programs in Systems and Information Engineering Graduate School of Science Annd Technology University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan Institute of Systems and Information Engineering University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki305-8573 Japan

ISBN: (纸本)9798350373332

The purpose of this study is to develop and investigate a new rough clustering based on optimization. We propose a restructured algorithm using only one variable, instead of the algorithm described using two variables in existing methods. We also perform numerical examples using artificial data and the Iris and Wine datasets. This research has the potential to be used as a method for determining false negatives and false positives in cancer diagnosis. © 2024 IEEE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Influence of road environmental elements on pedestrian and cyclist road crossing behaviour

引用

sICE Journal of Control, Measurement, and system Integration 2021年第2期14卷 50-58页

作者： saito, Yuichi Kochi, Fuma Itoh, Makoto Fushima, Takesato sugano, Takashi Yamamoto, Yasunori Faculty of Engineering Information and Systems University of Tsukuba Tsukuba Japan Master's Program in Risk and Resilience Engineering University of Tsukuba Tsukuba Japan Mazda Motor Corporation Hiroshima Japan

The pedestrian and cyclist-related accident fatality rate is higher than that of other traffic accidents. One of the pedestrian behaviours that leads to traffic accidents is the act of moving rapidly onto the road from a blind spot without warning. Expert drivers practice hazard-anticipatory driving and will naturally seek to reduce uncertainty by attempting to fit their current driving context into a pre-existing category. risk management is the process of identifying hazards and assessing and controlling risks to attain safety. The purpose of this study was to evaluate the influence that driving context-altering road environmental elements exert on the road-crossing behaviour of pedestrians and cyclists. Thus, this study attempted to identify covert hazards (obscured pedestrians and cyclists). A logistic regression analysis was employed along with data from the near-miss incident database, in which approximately 140,000 near-crash-relevant events were registered in 2017. By using the logistic regression analysis along with the annotations recorded in the database, we constructed a predictive model to identify covert hazards. The study demonstrated the feasibility of using a set of environmental elements that shape the driving context to construct a predictive model that identifies covert hazards. © 2021 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

On a New Rough Clustering Based on Optimization

On a New Rough Clustering Based on Optimization

引用

International symposium on soft Computing and Intelligent systems (sCIs)

作者： sakuya FURUTA Yasunori ENDO Master's Program in Risk and Resilience Engineering Degree Programs in Systems and Information Engineering Graduate School of Science annd Technology University of Tsukuba Ibaraki Japan Institute of Systems and Information Engineering University of Tsukuba Ibaraki Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

关键词： Iris Accuracy Clustering algorithms Computational complexity Optimization Cancer

来源：评论

学校读者我要写书评

暂无评论

A Note on Even-sized spectral Clustering

A Note on Even-Sized Spectral Clustering

引用

International symposium on soft Computing and Intelligent systems (sCIs)

作者： Hiroki MIYAKAWA Yasunori ENDO Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master's Program in Risk and Resilience Engineering University of Tsukuba Tsukuba Ibaraki Japan Institute of Systems and Information Engineering University of Tsukuba Tsukuba Ibaraki Japan

ISBN: (数字)9798350373332

ISBN: (纸本)9798350373349

关键词： Clustering algorithms Partitioning algorithms Classification algorithms Optimization Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Preference-based jogging route selection in downtown Tokyo

引用

Cities and Health 2024年第3期8卷 390-404页

作者： Huang, Yumeng Eom, sunyong suzuki, Tsutomu Master’s Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Division of Policy and Planning Sciences Institute of Systems and Information Engineering University of Tsukuba Tsukuba Japan

Jogging has become a popular urban outdoor recreational activity because it is inexpensive and easy. Although there are positive responses to leisure-route planning from many regions, the routes with features preferred by joggers are not commonly considered in urban planning. This article explores and evaluates methods for determining optimal urban jogging routes while considering joggers’ preferences. This study combines information about road width, green space, riverbank scenery, and various points of interest with jogging heat map data and uses a decision tree analysis to study joggers’ preferences. Next, routes with high potential considering three different patterns of points of interest and road width are selected using the vehicle routing problem analysis in ArcGIs. This method for preference-based route selection can be used to identify which links in urban road networks are attractive to runners and provide policymakers with useful information for designing built environments. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Jogger preferences jogging route selection urban outdoor recreation vehicle routing problem

来源：评论

学校读者我要写书评

暂无评论

Influence of Information about Minimal risk Maneuvers on Driver Behavior during Conditional Driving Automation

引用

International Journal of Automotive engineering 2022年第3期13卷 122-131页

作者： Ichinose, Yusaku Zhou, Huiping saito, Yuichi Itoh, Makoto Master's Program in Risk and Resilience Engineering University of Tsukuba 1-1-1 Tennoudai Tsukuba Ibaraki305-8573 Japan Faculty of Engineering Information and Systems University of Tsukuba 1-1-1 TennoudaiTsukuba Ibaraki305-8573 Japan

In Japan, the guidelines of safety technology for automated vehicles clearly state the requirement of level-3 equipment with minimal risk maneuver (MRM) in automated vehicles. In case the drivers fail to respond to a request for intervention, the conditional driving automation system activates an MRM to control the vehicle to a halt in the driving lane or on the side of the road. The current study aims to explore the research question: how does the information of the MRM functionality equipped within the automated vehicle affect the driver behavior during conditionally automated driving? In this study, we hypothesized that drivers who are provided with information about MRM functionality may reduce their attention toward the surrounding environment. The attention allocation to the surrounding environment may be related to the quality of take-over performance. Therefore, we attempted to observe the drivers' takeover performance in response to RtI. Accordingly, a driving simulator experiment was conducted with 28 drivers as participants to investigate the influence of information regarding MRM on driver behavior. Two groups were formed by randomly placing the participants with and without providing MRM information. The results revealed that the information on MRM triggered a behavioral change in the drivers and reduced their attention toward the surrounding environment or allocated more attention toward the surrounding environment. In future, we would examine the method and content of communicating the MRM information to drivers using automated driving systems. © 2022. society of Automotive Engineers of Japan, Inc. All Rights Reserved.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Even-sized clustering with noise clustering method

Even-sized clustering with noise clustering method

引用

International symposium on Advanced Intelligent systems

作者： Kei Kitajima Yasunori Endo Master’s Program in Risk Engineering University of Tsukuba Ibaraki Japan Faculty of Engineering Information and Systems University of Tsukuba Ibaraki Japan

ISBN: (纸本)9781538626344;9781538626337

Clustering is a method of data analysis without the use of supervised data. Clustering method focusing on cluster size is expected to be useful for task distribution problems and several methods have been proposed. We proposed Fuzzy Even-sized Clustering Based on Optimization (FECBO) and COntrolled-sized Clustering Based on Optimization as a method focusing on cluster size. However, these methods have the problem that they are susceptible to noise. It is believed that this issue can be overcome by applying noise clustering method. Noise clustering is a method that it classify noise into noise clusters. In this study, we extend FECBO and COCBO with noise clustering and verify its effectiveness through numerical examples.

关键词： Clustering Machine learning Even-sized Noise clustering

来源：评论

学校读者我要写书评

暂无评论

A Note on Brake system of Train set with Wheel slide Protection system

A Note on Brake System of Train Set with Wheel Slide Protect...

引用

International symposium on soft Computing and Intelligent systems (sCIs)

作者： Yuya Kanazawa Yasunori Endo shin-Ichi Nakazawa Daisuke Hijikata Master’s Program in Risk Engineering University of Tsukuba Ibaraki Japan Faculty of Engineering Information and Systems University of Tsukuba Ibaraki Japan Railway Technical Research Institute Tokyo Japan

ISBN: (纸本)9781538626344;9781538626337

In railways, brake control is the important factor on safety, punctuality and etc. However, the slip is likely to occur during brake control since the wheels and rails are made of metal. The slip makes the brake distance longer and the wheels damaged. The condition of the slip is mainly due to various factors such as the load, the state of the contact surface between the wheels and the rails, so the slip becomes a high uncertainty matter. Actual train uses the blending control of regenerative brake and pneumatic brake for wheel-slide-protection (WsP), but it can be more efficient to divide braking force because each of them performs independent. In this paper, we will construct a system that distributes braking force throughout the entire train set including not only pneumatic brake but also regenerative brake. And we will evaluate of the train set brake control with electro-pneumatic blending control.

关键词： Brakes Force Wheels Rail transportation Fuzzy logic Axles Rails

来源：评论

学校读者我要写书评

暂无评论

On Linear Clustering with Constraints on Cluster size

On Linear Clustering with Constraints on Cluster Size

引用

International symposium on Advanced Intelligent systems

作者： Naoya Kimoto Yasunori Endo Master’s Program in Risk Engineering University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki Japan Faculty of Engineering Information and Systems University of Tsukuba 1-1-1 Tennodai Tsukuba Ibaraki Japan

ISBN: (纸本)9781538626344;9781538626337

Clustering is unsupervised classification method in the field of machine learning. c-varieties (CV) and c-regression (CR) are linear clustering that can find linear structures of a dataset. CV and CR are clustering algorithms that perform principal component analysis and regression analysis at the same time, respectively. By the way, when clustering is used in the actual society, there are situations where the number of objects in each cluster is restricted. In this paper, we propose new linear clustering algorithms with constraints on cluster size.

关键词： Clustering Linear structure Constraints on cluster size

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：